A data fast acquisition method for real scene three-dimensional technology

Abstract

The application provides a data rapid acquisition method for real scene three-dimensional technology. The method belongs to the technical field of data acquisition and comprises the following steps: acquiring original data through a multi-source sensor-based data acquisition system, planning and scheduling the original data acquisition task by using a cloud computing platform and combining GIS data; in the data acquisition process, performing real-time preprocessing on the original data through an edge computing node, fusing the multi-source original data through a data fusion algorithm, and generating a three-dimensional model; using an artificial intelligence algorithm to automatically optimize and correct the fused three-dimensional model; and combining light simulation and texture mapping technology to enhance the reality and visual effect of the model. Through planning and scheduling based on the cloud computing platform and GIS data, the task and time window of data acquisition can be accurately determined, thereby improving the efficiency and accuracy of data acquisition.

Description

TECHNICAL FIELD

[0001] The application provides a data rapid acquisition method for real scene three-dimensional technology, and belongs to the technical field of data acquisition. BACKGROUND

[0002] In the rapid development of real scene three-dimensional technology today, high-precision and high-efficiency data acquisition and processing have become the key to promoting the development of smart cities, cultural heritage protection, digital twins and other fields. Traditional data acquisition methods often rely on a single sensor, such as a laser scanner or a camera. Such methods not only have slow data acquisition speed and high cost, but also have difficulty in ensuring data integrity and precision in complex environments (such as large changes in light and severe occlusion). In addition, the data processing process usually needs to be carried out in a data center, which not only increases the delay of data transmission, but also may cause a large amount of data to be lost or damaged during transmission, affecting the precision and practicality of the final three-dimensional model.

[0003] With the rapid progress of Internet of Things, cloud computing, edge computing and artificial intelligence technology, a new solution is provided for data acquisition and processing of real scene three-dimensional technology. Multi-source sensor fusion technology can fully utilize the advantages of different sensors in data acquisition, such as the high precision of laser scanners and the rich color information of cameras, thereby significantly improving the comprehensiveness and accuracy of data. At the same time, cloud computing platforms can realize remote planning and efficient scheduling of data acquisition tasks due to their powerful data processing capabilities and flexibility, optimize resource allocation, and reduce manual intervention. SUMMARY

[0004] The application provides a data rapid acquisition method for real scene three-dimensional technology to solve the problems mentioned in the background art.

[0005] The application provides a data rapid acquisition method for real scene three-dimensional technology, which comprises the following steps:

[0006] S1, acquiring original data by a multi-source sensor-based data acquisition system, planning and scheduling the original data acquisition task by using a cloud computing platform and combining with GIS data;

[0007] S2, during the data acquisition process, pre-processing the original data in real time by an edge computing node, fusing the multi-source original data by a data fusion algorithm, and generating a three-dimensional model;

[0008] S3, using an artificial intelligence algorithm to automatically optimize and correct the fused three-dimensional model, and combining with light simulation and texture mapping technology to enhance the realism and visual effect of the model;

[0009] S4, monitoring the whole process of data acquisition and processing through a real-time monitoring system; dynamically adjusting the data acquisition and processing strategy according to the real-time feedback data.

[0010] Further, the S1 comprises:

[0011] S11, determining the purpose and demand of data acquisition, screening data sources from multiple GIS data sources; and preprocessing the selected GIS data;

[0012] S12, fusing the preprocessed GIS data to form a unified spatial database;

[0013] S13, and according to the demand analysis result, listing the related indicators of the required sensor to calibrate the selected sensor, and determining the sensor deployment scheme;

[0014] S14, based on the GIS data and the sensor deployment scheme, planning the data acquisition route, and setting the time window of data acquisition based on multiple factors; and formulating the cooperative working strategy among multiple source sensors;

[0015] S15, assigning the planned task to each sensor, and setting the task priority and execution order; establishing a real-time monitoring mechanism to monitor the working state of the sensor in real time through a wireless communication network;

[0016] S16, based on the real-time monitoring result, starting the emergency plan and processing the abnormal situation.

[0017] Further, the S12 comprises:

[0018] Convert GIS data from different sources into a unified format; and enhance the key features in the GIS data,

[0019] Perform data fusion operation based on the preset fusion scheme, and fuse the preprocessed GIS data using selected algorithms and tools;

[0020] Quality assessment of the fused data, according to the evaluation result, iterative optimization of the fusion algorithm or parameter;

[0021] Import the fused GIS data into the spatial database, and perform indexing and metadata management, security management of the data, and data backup strategy.

[0022] Further, the S2 comprises:

[0023] S21, selecting an edge computing node device according to the data processing demand; deploying an edge computing node at the data acquisition site, and connecting the edge computing node with the sensor through the Internet of Things;

[0024] S22, the edge computing node receives raw data from the sensor, checks data integrity and consistency, denoises the raw data through a filtering algorithm, and compresses the denoised data;

[0025] S23, through feature extraction and matching algorithm, the multi-source data is accurately matched, and through data fusion strategy, data fusion is carried out; the fused data is quality evaluated;

[0026] S24, based on the fused data, the data is reconstructed by using three-dimensional reconstruction algorithm; according to the reconstructed data, the preliminary three-dimensional model framework is generated, and the preliminary model is verified.

[0027] Further, the S3 comprises:

[0028] S31, the error in the three-dimensional model is classified and analyzed, and the error in the three-dimensional model is automatically identified by non-invasive identification algorithm;

[0029] S32, for different types of errors, corresponding elimination strategies are formulated;

[0030] S33, according to different regions and characteristics of the model, the sampling density is dynamically adjusted, the external auxiliary data is introduced, the existing data is fused, and the accuracy and integrity of the model are further improved;

[0031] S34, the repeated structure in the three-dimensional model is identified and processed, and the redundant information is reduced by algorithm optimization;

[0032] S35, based on physical principles and scene characteristics, a lighting model is constructed to simulate the lighting effect under different time and weather conditions;

[0033] S36, texture materials are obtained from a texture material library, and the texture materials are accurately mapped to the model surface based on texture mapping technology.

[0034] Further, the S33 comprises:

[0035] Through image processing and machine learning algorithm, the key feature area in the three-dimensional model is automatically identified, and according to the importance and complexity of the feature area, the sampling density of each area is dynamically planned;

[0036] Based on the planning result, an adaptive sampling algorithm is adopted to dynamically adjust the sampling density in the model construction or optimization process;

[0037] The external auxiliary data (ground control points, high-precision map) is obtained and preprocessed, and data fusion operation is performed, the external auxiliary data is fused with the existing three-dimensional model data; after the fusion is completed, the precision of the fusion result is evaluated;

[0038] The multi-source data is cross-verified to find and correct potential errors in the model, and the surface of the model is finely processed through surface reconstruction technology.

[0039] A real-time feedback mechanism is established to monitor and evaluate each link in the model construction and optimization process, and if problems or deficiencies are found, feedback and adjustment are made.

[0040] According to the real-time feedback result, an iterative optimization strategy is formulated, and the accuracy and detail performance of the model are improved through multiple iterations.

[0041] Further, the corresponding elimination strategy includes: for geometric errors, interpolation, smoothing or resampling is used for correction; for texture errors, texture repair, replacement or remapping is used to solve; for semantic errors, context information and prior knowledge are combined for adjustment.

[0042] Further, the S4 comprises:

[0043] S41, the data of each link is comprehensively monitored by a real-time monitoring system, and is gathered and integrated;

[0044] S42, real-time feedback data is collected by the monitoring system, the collected feedback data is deeply analyzed and evaluated, and potential problems and bottlenecks are identified;

[0045] S43, the analysis result is presented to the relevant personnel in a visual way, and a dynamic adjustment strategy is formulated based on the real-time feedback data and the change of project requirements;

[0046] S44, the formulated strategy is issued to each execution unit through the monitoring system, and the strategy is automatically executed;

[0047] S45, the strategy execution effect is evaluated and verified based on the execution result, and the strategy is adjusted and optimized according to the evaluation result.

[0048] The electronic device provided by the application comprises a memory, a processor and a computer program stored on the memory and capable of running on the memory, and the processor executes the program to realize the data fast acquisition method for real scene three-dimensional technology as described in any one of the above.

[0049] The non-transitory computer readable storage medium provided by the application stores a computer program, and the program is executed by a processor to realize the data fast acquisition method for real scene three-dimensional technology as described in any one of the above.

[0050] The application has the beneficial effects that: through planning and scheduling based on a cloud computing platform and GIS data, the task and time window of data collection can be accurately determined, thereby improving the efficiency and accuracy of data collection; the edge computing node can quickly generate a preliminary three-dimensional model through real-time preprocessing and fusion of data, so that the speed of data processing can be accelerated, and the redundancy and error of data can be reduced; the precision and quality of the three-dimensional model can be significantly improved through automatic optimization and correction using artificial intelligence algorithms; the realism and visual effect of the model can be enhanced through light simulation and texture mapping technology, so that the model is closer to the actual scene; the data collection and processing process can be comprehensively monitored through a real-time monitoring system, and the strategy can be dynamically adjusted according to real-time feedback data, so that problems in the process can be effectively responded to and solved; the real-time monitoring system can quickly discover abnormal conditions and start an emergency plan to ensure the stability and continuity of the data collection and processing process; a unified spatial database is formed through preprocessing and fusion of GIS data, which not only improves the integration of data, but also better manages and backs up the data; the accuracy and integrity of the data are ensured through quality evaluation and optimization of the fused data, and the final effect of the three-dimensional model is improved; the sampling density is dynamically adjusted according to the complexity of the key feature area, so that the model surface can be finely processed, and the detail performance of the model can be improved; the precision and details of the model can be improved through fusion of external auxiliary data and existing data, and potential errors can be reduced. BRIEF DESCRIPTION OF DRAWINGS

[0051] Figure 1 The method steps of the application are described. DETAILED DESCRIPTION

[0052] In order to more clearly understand the above-mentioned purposes, features and advantages of the present application, the present application will be described in detail below in combination with the drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0053] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application. The described embodiments are merely some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application.

[0055] An embodiment of the present application is as follows: Figure 1As shown, a data rapid acquisition method for real three-dimensional technology, the method comprises:

[0056] S1, through the data acquisition system based on multi-source sensor to collect raw data, using cloud computing platform and combining GIS data, the raw data acquisition task is planned and scheduled;

[0057] S2, in the process of data acquisition, through the edge computing node, real-time preprocessing of raw data, through data fusion algorithm, high-precision fusion of multi-source raw data, and generate three-dimensional model;

[0058] S3, using artificial intelligence algorithm, the fused three-dimensional model is automatically optimized and corrected; and combining with the light simulation and texture mapping technology, the reality and visual effect of the model are enhanced;

[0059] S4, through real-time monitoring system, the whole process of data acquisition and processing is monitored; according to the real-time feedback data, dynamically adjust the data acquisition and processing strategy. For example, when it is found that the data quality of a certain area is not good, the collection route can be adjusted or the collection density can be increased; when the bottleneck appears in the processing process, the algorithm parameters can be optimized or the computing resources can be increased.

[0060] The working principle of the above technical solution is as follows: multiple sensors including LiDAR, high-definition cameras, INS, etc. are used to obtain raw data of the target area from multiple dimensions and angles; combined with the prior knowledge of GIS, the powerful computing capability of the cloud computing platform is used to intelligently plan and schedule the data collection task. This includes determining the optimal collection path, time window, sensor configuration, etc. to improve the efficiency and accuracy of data collection; deploy edge computing nodes on the data collection site to preliminarily process the collected raw data, such as denoising, compression, etc. to reduce data transmission and speed up subsequent processing; use advanced data fusion algorithms to fuse data from different sensors with high precision. Through algorithm processing, eliminate the redundancy and contradiction between data, generate more complete and accurate three-dimensional point cloud data, and then build a preliminary three-dimensional model; apply artificial intelligence technologies such as deep learning and machine learning to automatically identify and correct errors, voids, repeated structures, etc. in the three-dimensional model. This process improves the accuracy and completeness of the model through continuous learning and iteration; in order to enhance the realism and visual effect of the model, use light simulation technology to simulate the changes of natural light, and at the same time use texture mapping technology to map high-resolution texture images to the surface of the three-dimensional model, making the model more realistic; through real-time monitoring system, monitor the whole process of data collection, preprocessing, model building, etc. to ensure the smooth progress of the whole process; according to the real-time feedback data such as data quality, processing speed, etc. dynamically adjust the data collection and processing strategy. For example, when it is found that the data quality of a certain area is poor, the collection route can be adjusted or the collection density can be increased immediately; when performance bottlenecks occur in the processing process, algorithm parameters can be optimized or computing resources can be increased to ensure the stability and efficiency of the whole system.

[0061] The technical scheme has the effects that: by integrating multiple sensors (such as LiDAR, high-definition camera, INS, etc.), rich raw data can be obtained from multiple dimensions and angles, thereby improving the comprehensiveness and accuracy of data collection; by using the powerful computing capability of the cloud computing platform and the prior knowledge of GIS data, intelligent planning and scheduling of the data collection task are performed, the efficiency and pertinence of the collection process are ensured, and the collection of redundant data is reduced; an edge computing node is deployed on the data collection site to realize real-time preprocessing of the raw data, reduce data transmission delay, and speed up subsequent processing; high-precision fusion of multiple source raw data generates an accurate three-dimensional model, providing a solid foundation for subsequent model optimization and correction; errors, voids, repeated structures and other problems in the three-dimensional model are automatically identified and corrected, significantly improving the accuracy and integrity of the model. At the same time, combined with light simulation and texture mapping technology, the realism and visual effect of the model are enhanced, making it more realistic; the whole process of data collection and processing is monitored to ensure the smooth progress of the whole process. Through real-time feedback data, problems are found and solved in time; according to the real-time feedback data, the data collection and processing strategy is dynamically adjusted, such as adjusting the collection route, increasing the collection density, optimizing the algorithm parameters or increasing the computing resources, to improve the flexibility and adaptability of the system; through the highly integrated and optimized data collection, processing, optimization and monitoring process, manual intervention and repetitive labor are reduced, and the overall cost is reduced; the efficient data collection and processing capability enables the technical scheme to quickly respond to market demand and provide high-quality real three-dimensional data support for various application scenarios.

[0062] In an embodiment of the present application, the S1 comprises:

[0063] S11, the purpose and demand of data collection are determined, and data sources with strong relevance and high data quality related to the target area are selected from multiple GIS data sources; and the selected GIS data is preprocessed,

[0064] S12, the preprocessed GIS data is fused to form a unified spatial database;

[0065] S13, and according to the demand analysis result, the related indicators of the required sensor are listed, including model, specification, performance parameter, etc. The selected sensor is calibrated, and the sensor deployment scheme is determined, including deployment position, height, angle, scanning range, etc.

[0066] S14, based on the GIS data and the sensor deployment scheme, the optimal data collection route is planned, and based on multiple factors including weather conditions, light conditions, traffic conditions, the time window of data collection is set; and the cooperative working strategy among multiple source sensors is formulated;

[0067] S15, assign the planned tasks to each sensor and set the task priority and execution order; establish a real-time monitoring mechanism to monitor the working state of the sensor in real time through a wireless communication network;

[0068] S16, based on the real-time monitoring results, start the emergency plan and handle the abnormal situation (such as sensor failure, data loss, etc.).

[0069] The working principle of the above technical solution is as follows: first, the specific purpose and actual demand of data collection are determined, which is the basis of the whole data collection work; from multiple GIS data sources, select the data source with strong correlation and high data quality related to the target area. This step ensures that the data basis for subsequent work is reliable and accurate; clean the selected GIS data, remove duplicate, incorrect or irrelevant information. The preprocessing process improves the quality of the data, and provides strong support for subsequent data fusion and collection route planning; fuse the preprocessed GIS data to form a unified spatial database. This step makes data from different sources can be used and analyzed in a unified framework; according to the demand analysis result, list the related indexes of the required sensor, including model, specification, performance parameter, etc.; calibrate the selected sensor to ensure its measurement accuracy and stability. This step is the key to ensure the accuracy of data collection; including deployment location, height, angle, scanning range, etc., to ensure that the sensor can cover the target area and obtain effective data; based on GIS data and sensor deployment scheme, plan the optimal data collection route. This step considers various factors, such as weather conditions, light conditions, traffic conditions, etc., to ensure the efficiency and safety of data collection; set the time window of data collection according to various factors to avoid unfavorable conditions and make full use of favorable opportunities; ensure the collaborative work of multiple source sensors to ensure the continuity and consistency of data collection; assign the planned tasks to each sensor and set the task priority and execution order. This step ensures the orderly progress of data collection; monitor the working state of the sensor in real time through a wireless communication network. This helps to discover and handle abnormal situations in time; based on the real-time monitoring results, start the emergency plan and handle the abnormal situation (such as sensor failure, data loss, etc.). This ensures the continuity and stability of data collection.

[0070] The effect of the above technical scheme is: by screening out the data source with strong correlation and high data quality from the multiple GIS data sources related to the target area, and performing cleaning processing, effectively removing repeated, incorrect or irrelevant information, thereby improving the accuracy and reliability of subsequent data processing and modeling; the preprocessed GIS data is fused to form a unified spatial database, which helps to eliminate redundancy and contradictions between data, and provides a unified and consistent data basis for data collection and model construction; according to the demand analysis result, the related indicators of the required sensor are listed and calibrated, so as to ensure the measurement accuracy and stability of the sensor. At the same time, the reasonable sensor deployment scheme, including deployment position, height, angle, scanning range, etc., makes the data collection more comprehensive and accurate; based on the GIS data and the sensor deployment scheme, the optimal data collection route is planned, which not only improves the efficiency of data collection, but also reduces unnecessary resource consumption. At the same time, considering the weather conditions, light conditions, traffic conditions and other multi-factor setting data collection time window, the smooth progress of data collection is ensured; the cooperative working strategy among multiple sensors is formulated to ensure the continuity and consistency of data collection, avoiding the problem of data missing or repeated collection; the planned task is assigned to each sensor, and the task priority and execution order are set, so that the data collection work is orderly carried out; a real-time monitoring mechanism is established, and the working state of the sensor is monitored in real time through the wireless communication network, which can timely discover and handle abnormal situations such as sensor failure and data loss, and ensure the continuity and stability of data collection; based on the real-time monitoring result, the emergency plan is started and handled for the abnormal situation, which reduces the data collection interruption or quality problem caused by abnormal situation, and improves the stability and reliability of the whole data collection process.

[0071] In one embodiment of the present application, the S12 comprises:

[0072] The GIS data of different sources is converted into a unified format; and the key features in the GIS data are enhanced, such as edge detection, texture enhancement, etc., to improve the information richness and recognition of the data.

[0073] Based on the preset fusion scheme, the data fusion operation is performed, and the preprocessed GIS data is fused by using selected algorithms and tools;

[0074] The quality of the fused data is evaluated, including accuracy verification and consistency check, to ensure that the fusion result meets the expected requirements; and the fusion algorithm or parameter is iteratively optimized according to the evaluation result;

[0075] The fused GIS data is imported into a spatial database, and indexed and metadata managed, and the data is safely managed, such as encrypted storage, access control, etc., and a data backup strategy is formulated.

[0076] The working principle of the above technical solution is to convert GIS data of different sources and formats into a unified format. This is the premise of data fusion, ensuring seamless integration and mutual operation between different data sources; key features in GIS data are enhanced, such as edge detection to highlight geographical boundaries and texture enhancement to improve the recognition of surface coverings. These processes aim to improve the information richness and recognition of data, providing more valuable information for subsequent data analysis and modeling; based on the preset fusion scheme, selected algorithms and tools are used to fuse the preprocessed GIS data. This step may involve complex operations such as spatial matching and attribute merging between multiple data sources, aiming to generate a unified data set containing more comprehensive and accurate information; quality assessment of the fused data, including precision verification and consistency check. These evaluation methods are used to ensure that the fusion results meet the expected requirements, such as data accuracy, completeness and consistency; based on the evaluation results, the fusion algorithm or parameters are iteratively optimized. If the evaluation finds deficiencies in the fusion results, algorithm parameters can be adjusted or different fusion strategies can be tried to achieve better fusion results; the fused GIS data is imported into a spatial database and indexed and metadata managed. Indexing can speed up data retrieval and query speed, while metadata provides detailed descriptions of data sources, content, quality and other information; data security management, such as encrypted storage to prevent data leakage and access control to ensure that only authorized users can access the data. At the same time, data backup strategies are developed to prevent data loss or damage.

[0077] The above technical solution achieves the following effects: It converts GIS data from different sources into a unified format, eliminating format differences and enhancing data consistency and interoperability. This makes data exchange and sharing between different systems and platforms easier and more efficient. It enhances key features in GIS data, such as edge detection and texture enhancement, improving the data's information richness and recognizability. This not only improves the visual effect of the data but also provides a more accurate and detailed information foundation for subsequent data analysis and modeling. It performs data fusion operations based on a preset fusion scheme, using selected algorithms and tools to fuse pre-processed GIS data. This process integrates information from multiple data sources, generating a unified dataset containing more comprehensive and accurate information. By evaluating the quality of the fused data, including accuracy verification and consistency checks, potential problems during the fusion process can be identified and corrected in a timely manner. Iterative optimization of the fusion algorithm or parameters based on the evaluation results further improves the fusion effect, ensuring that the fusion results meet expected requirements. Finally, it imports the fused GIS data into a spatial database for indexing and metadata management. This not only facilitates data retrieval and querying but also improves data management efficiency. Meanwhile, metadata management allows for detailed recording of data sources, content, and quality, providing crucial references for data use and maintenance. Data security management, such as encrypted storage and access control, effectively prevents data leaks and unauthorized access. Developing data backup strategies ensures rapid recovery in case of data loss or corruption, guaranteeing data integrity and availability. Through S12-stage data processing, information from multiple data sources can be integrated to form more comprehensive and accurate geographic information. This provides strong support for decision-making in areas such as urban planning, environmental protection, and disaster early warning. Decision-makers can make more scientific and rational decisions based on this data, improving the accuracy and effectiveness of their decisions.

[0078] In one embodiment of the present invention, step S14 includes:

[0079] Based on the spatial analysis function of GIS data, key areas and potential risk points for data collection were identified; based on the results of the requirements analysis, the selection criteria for sensors were further refined.

[0080] Using GIS spatial optimization algorithms, the deployment locations of sensors can be precisely planned;

[0081] Based on GIS-based path planning capabilities, the system dynamically generates optimal data collection routes; it also uses heuristic search algorithms or machine learning models to predict the best path.

[0082] According to the periodicity, seasonal characteristics of data changes, and the influence of specific events (such as natural disaster warning, major event preparation), set the time window of data collection;

[0083] Develop detailed multi-source sensor collaboration protocol, use cloud computing or edge computing platform to realize real-time processing and fusion of sensor data, at the same time, design failover and backup mechanism to ensure that the whole data collection system can still run stably when individual sensors fail.

[0084] The working principle of the above technical solution is as follows: using the spatial analysis module of GIS software, such as buffer analysis (generating a certain width of area around a specific point or line) and overlay analysis (overlaying the data of two or more layers according to the spatial position to generate new spatial information), combined with topography, vegetation cover, hydrological conditions and other multi-source GIS data, comprehensive analysis is carried out; by fusing GIS data of different dimensions, the key areas of data collection are identified, which may be sensitive areas of environmental change, ecologically fragile areas or densely populated areas of human activities. At the same time, potential risk points such as geological disaster prone areas and areas near pollution sources are analyzed to provide scientific basis for subsequent sensor deployment and data collection; according to the demand analysis results, the specific requirements of data collection are clarified, such as measurement parameters, accuracy requirements, etc. Then, combined with the physical parameters (measurement range, accuracy, resolution) and environmental adaptability (waterproof, dustproof, high / low temperature resistance) of the sensor, the sensor is selected. At the same time, considering the data transmission mode (wired / wireless) and energy efficiency, the sensor can work stably in complex environment and meet the long-term monitoring requirements; using the spatial optimization algorithm of GIS, such as genetic algorithm or simulated annealing algorithm, combined with factors such as terrain complexity, signal coverage and traffic accessibility, the deployment location of the sensor is accurately planned. Through iterative calculation of the algorithm, the optimal deployment scheme is found to ensure that the mutual exclusion and cooperation relationship between sensors is properly handled, avoiding data redundancy and blind area, and realizing full coverage and efficiency of the data collection network; based on the path planning function of GIS, combined with real-time traffic information, weather forecast, personnel / vehicle scheduling and other factors, the optimal data collection route is dynamically generated. Using heuristic search algorithm or machine learning model (such as deep learning network) to predict the best path can reduce the time cost and resource consumption in the collection process. At the same time, the feasibility and safety of the path are considered to ensure the smooth progress of the data collection task; according to the periodicity, seasonality and influence of specific events of data change, the time window of data collection is flexibly set. Time series analysis and trend prediction methods are used to analyze the rules and trends of data change to determine the best time for data collection. In critical moments such as natural disaster warning and major event preparation, the frequency and density of data collection are increased to obtain more comprehensive data support; a detailed multi-source sensor cooperation protocol is developed to clarify the data synchronization mechanism, conflict resolution strategy and data fusion algorithm between sensors. Through the protocol, the behavior and data exchange of the sensor are standardized to ensure efficient cooperation between sensors; using the high-performance computing capability of cloud computing or edge computing platform, real-time processing and fusion of sensor data are realized. Through data cleaning, deduplication and fusion, the accuracy and integrity of the data are improved. At the same time, multi-source data are integrated and analyzed by using data fusion algorithm to mine deeper information and value; a failover and backup mechanism is designed to cope with the failure of individual sensors.When a sensor fails, the system can automatically switch to a backup sensor or adjust the collection tasks of other sensors to compensate for data loss. At the same time, regular maintenance and calibration of sensors are carried out to ensure their long-term stable operation.

[0085] The effect of the above technical solution is: through the spatial analysis function of GIS data combined with multi-dimensional information, the key areas and potential risk points of data collection can be accurately identified. This helps to concentrate limited resources in the areas that need the most attention, improving the efficiency and accuracy of data collection; based on the demand analysis results, the selection criteria of the sensor are refined to ensure that the selected sensor can accurately meet the data collection requirements. This helps to reduce resource waste and data errors caused by insufficient or excessive performance of the sensor; using the spatial optimization algorithm of GIS, combined with multiple factors, the deployment position of the sensor is accurately planned. This helps to avoid data redundancy and blind spots, ensuring full coverage and efficiency of the data collection network; based on the path planning function of GIS, combined with real-time traffic information, weather prediction and other factors, the optimal data collection route is dynamically generated. This helps to reduce the time cost and resource consumption in the collection process, improving the flexibility and efficiency of data collection; according to the periodicity, seasonality characteristics of data changes and the influence of specific events, the time window of data collection is flexibly set. This helps to ensure data collection in periods of significant data changes or urgent needs, improving the timeliness and value of data; through time series analysis and trend prediction methods, the trend and regularity of data changes are predicted, which helps to collect data at the best time, thereby improving the accuracy and reliability of data; detailed multi-source sensor cooperation protocol is formulated to clarify the data synchronization mechanism, conflict resolution strategy and data fusion algorithm between sensors. This helps to ensure efficient cooperation between sensors, improving the overall efficiency of data collection; using cloud computing or edge computing platform to realize real-time processing and fusion of sensor data improves the efficiency and accuracy of data processing. This helps to quickly obtain valuable information to support decision-making; design a failover and backup mechanism to deal with individual sensor failures. This helps to ensure that the entire data collection system can still operate stably when a sensor fails, reducing the risk of data loss and interruption; through comprehensive consideration of multiple factors in sensor deployment and path planning decisions, the adaptability of the data collection system to complex environments is improved. This helps to ensure that the system can operate stably and meet data collection requirements under various conditions.

[0086] In one embodiment of the present application, the S15 comprises:

[0087] Refine the overall data collection task into multiple sub-tasks, and prioritize the sub-tasks;

[0088] According to the physical characteristics, measurement range, precision, and other parameters of the sensors, as well as the specific requirements of the sub-tasks, the tasks are assigned to the most suitable sensors; and the task allocation scheme is optimized

[0089] A detailed execution plan is formulated for each sensor, and the wireless communication network configuration is optimized;

[0090] A real-time data acquisition monitoring platform is established, integrating GIS maps, sensor status display, data acquisition progress tracking, and other functions. Through this platform, the real-time working status of each sensor, data acquisition progress, and data quality information can be intuitively viewed.

[0091] An abnormality detection threshold is set, and when the sensor working status appears abnormal (such as low battery, signal interruption, data anomaly, etc.), the system automatically triggers a pre-warning or alarm mechanism; relevant personnel are notified through SMS, email, and other means;

[0092] Possible abnormal types are identified and classified, such as sensor failure, data transmission interruption, data quality problems, etc. For different types of abnormalities, corresponding handling procedures and emergency plans are formulated.

[0093] For some automatically recoverable abnormalities (such as temporary network interruption), an automatic troubleshooting and recovery mechanism is designed. By restarting the sensor, switching communication paths, etc., attempts are made to restore the normal working status of the sensor.

[0094] For abnormalities that cannot be automatically recovered, a manual intervention process is started. Professional personnel are notified to go to the scene for inspection and repair to ensure that the sensor resumes normal operation as soon as possible. At the same time, the data acquisition plan is adjusted to ensure the continuity and integrity of data acquisition.

[0095] The working principle of the above technical solution is as follows: the overall data collection task is divided into multiple specific sub-tasks, each of which clearly defines the specific area, data type and collection frequency of data collection, and other key information. This helps better manage and execute each task, ensuring the comprehensiveness and accuracy of the data; according to the urgency of the task, the importance of the data and the availability of resources, etc., the sub-tasks are prioritized. This ensures that critical tasks can be executed first, thereby improving the efficiency and response speed of data collection; according to the physical characteristics of the sensor (such as measurement range, accuracy, etc.) and the specific requirements of the sub-task, the task is assigned to the most suitable sensor. This ensures that the sensor can accurately and efficiently complete the task; when assigning tasks, the geographical location and signal coverage of the sensor should also be considered. By optimizing the task allocation scheme, the delay and energy consumption of data transmission can be reduced, and the stability and efficiency of data transmission can be improved; a detailed execution plan is developed for each sensor, including the start time, end time, data collection interval and data transmission method. These plans should take into account external factors such as weather changes, traffic conditions, etc. to ensure smooth execution of the task; optimize the configuration of the wireless communication network to ensure stable and reliable data transmission between the sensor and the monitoring center. Adopting multi-path transmission, automatic reconnection and other mechanisms can improve the anti-interference ability and fault tolerance of data transmission, and reduce the risk of data transmission interruption; establish a real-time data collection monitoring platform, integrating GIS maps, sensor status display and data collection progress tracking functions. Through this platform, the real-time working status and data collection situation of each sensor can be visually viewed, and potential problems can be discovered in a timely manner; set an abnormal detection threshold, when the sensor working status appears abnormal (such as low battery, signal interruption, data anomaly, etc.), the system automatically triggers the early warning or alarm mechanism. Through SMS, email and other means, relevant personnel are notified in a timely manner to take measures for processing; identify and classify the types of possible abnormalities and develop corresponding processing procedures and emergency plans. For some abnormalities that can be automatically recovered, an automatic fault diagnosis and recovery mechanism is designed; for abnormalities that cannot be automatically recovered, a manual intervention process is started to ensure that the sensor resumes normal operation as soon as possible; when a sensor fails or appears abnormal, the data collection plan is adjusted in a timely manner to ensure the continuity and integrity of data collection. By reallocating tasks, adjusting collection frequency, etc., the impact of sensor failure on data collection work is reduced.

[0096] The technical scheme has the following effects: by refining the overall task into multiple sub-tasks and prioritizing according to the urgency, data importance and resource availability, key tasks can be executed first, thereby improving the overall efficiency of data collection; by allocating tasks according to the physical characteristics of the sensors and the specific requirements of the sub-tasks, each sensor can be ensured to perform at its maximum efficiency, avoiding resource waste. At the same time, considering the optimization of geographical location and signal coverage can reduce the delay and energy consumption of data transmission, further improving resource utilization efficiency; detailed execution plans take into account external factors such as weather changes and traffic conditions, which helps to reduce data collection errors caused by external factors and ensure data accuracy and reliability; by integrating GIS maps, sensor status displays and data collection progress tracking functions, the working status and data collection of each sensor can be monitored in real time, and data quality problems can be discovered and handled in a timely manner; optimizing wireless communication network configuration, using multi-path transmission and automatic reconnection mechanisms can improve the anti-interference ability and fault tolerance of data transmission, reduce the risk of data transmission interruption, and improve the stability and reliability of the system; setting an abnormality detection threshold and automatically triggering a warning or alarm mechanism can quickly detect and handle sensor working state abnormalities, prevent problems from escalating, and ensure stable operation of the system; for some automatically recoverable abnormalities, an automatic fault diagnosis and recovery mechanism is designed to quickly restore the normal working state of the sensor, reduce the need for manual intervention, and improve the response speed and recovery ability of the system; for abnormalities that cannot be automatically recovered, a manual intervention process is started to notify professional personnel to go to the scene for inspection and repair, ensuring that the sensor returns to normal operation as soon as possible and ensuring the continuity and integrity of data collection; the establishment of a real-time data collection monitoring platform allows managers to visually view the real-time working status and data collection of each sensor, facilitating unified management and scheduling, and improving management efficiency.

[0097] In one embodiment of the present application, the S2 comprises:

[0098] S21, selecting an edge computing node device according to data processing requirements; deploying an edge computing node at the data collection site and connecting the edge computing node with the sensor through the Internet of Things;

[0099] S22, the edge computing node receives raw data from the sensor, checks the data integrity and consistency, performs denoising processing on the raw data through a filtering algorithm, and performs compression processing on the denoised data;

[0100] S23, precise matching of multi-source data is performed through feature extraction and matching algorithms, and data fusion is performed through data fusion strategies including fusion sequence, fusion algorithm selection, fusion parameter setting, etc.; quality evaluation is performed on the fused data;

[0101] S24, based on the fused data, reconstructing the data using a three-dimensional reconstruction algorithm; generating a preliminary three-dimensional model framework according to the reconstructed data, and verifying the preliminary model.

[0102] The working principle of the above technical solution is as follows: according to the specific requirements of data processing (such as computing power, storage requirements, power consumption limitations, etc.), select appropriate edge computing node devices. These devices usually have high processing performance, low power consumption and compact design, suitable for deployment in data acquisition sites; deploy edge computing nodes in the data acquisition site, and connect the edge computing nodes with various sensors through Internet of Things technology. This connection mode ensures real-time transmission and efficient processing of data, reduces data transmission delay and bandwidth consumption; the edge computing node receives the original data from the sensor, first checks the data integrity and consistency to ensure the accuracy and reliability of the data; through the filtering algorithm, the original data is denoised to remove noise and interference signals in the data and improve data quality. This step is crucial for subsequent data analysis and processing; the compressed data is compressed to reduce data transmission and reduce network bandwidth occupation. At the same time, the selection of compression algorithm should ensure that important information is not lost during compression; through feature extraction and matching algorithm, multi-source data from different sensors are accurately matched. These algorithms can identify common features and differences in data, providing a basis for data fusion; according to the preset fusion strategy (including fusion order, fusion algorithm selection, fusion parameter setting, etc.), the multi-source data is fused. In the fusion process, the weight, correlation and other factors of the data need to be considered to ensure the accuracy and reliability of the fusion result; the quality of the fused data is evaluated, including accuracy verification, consistency check, etc. Through the evaluation result, problems that may exist in the fusion process can be found and corrected in time to ensure the accuracy and reliability of the fusion result; based on the fused data, the data is reconstructed using a three-dimensional reconstruction algorithm. This step involves complex calculations, including spatial coordinate conversion, surface reconstruction, etc., to generate a preliminary three-dimensional model framework; the preliminary three-dimensional model is verified to ensure that it meets the basic geometric and spatial relationship requirements. The verification process may include geometric consistency check of the model, verification of spatial position relationship, etc. to ensure the accuracy and reliability of the model.

[0103] The technical scheme has the following effects: by deploying edge computing nodes in the data collection site, real-time processing of data is realized. Compared with the traditional cloud computing mode, edge computing reduces the delay of data transmission to the cloud, speeds up the data processing speed, and enables the system to respond to real-time events more quickly; the edge computing node checks the integrity and consistency of the raw data from the sensor and performs denoising processing through a filtering algorithm, effectively improving the data quality. This reduces subsequent processing errors caused by data errors or noise interference; the compressed data after denoising significantly reduces the data transmission amount. This not only reduces the occupation of network bandwidth, but also improves the efficiency of data transmission, which is particularly important in bandwidth-limited environments; through feature extraction and matching algorithms, multi-source data is accurately matched. This step ensures that information between different data sources can be correctly matched and integrated, providing a basis for subsequent data fusion; data fusion is performed according to the preset fusion strategy (including fusion order, fusion algorithm selection, fusion parameter setting, etc.). This strategic fusion method can fully consider the characteristics and needs of the data, ensuring the accuracy and reliability of the fusion results; based on the high-quality data after fusion, three-dimensional reconstruction algorithms are used to reconstruct the data. This process can generate accurate and detailed three-dimensional models, providing strong support for subsequent decision analysis and visualization; the preliminary three-dimensional model is verified to ensure that it meets the basic geometric and spatial relationship requirements. This step guarantees the accuracy and reliability of the model, providing a solid foundation for subsequent applications; the deployment of edge computing nodes makes data processing closer to the data source, reducing resource consumption during data transmission. At the same time, the computing power of the edge computing node provides additional resource support for the system, improving the overall performance of the system; since the edge computing node has independent processing and storage capabilities, when a node fails, other nodes can take over its work, ensuring the continuity and stability of the system. This fault-tolerant design improves the reliability and availability of the system.

[0104] In one embodiment of the present application, the S3 includes:

[0105] S31, classifying and analyzing errors in the three-dimensional model, such as geometric errors, texture errors, and semantic errors, and automatically identifying errors in the three-dimensional model through non-invasive recognition algorithms;

[0106] S32, formulating corresponding elimination strategies for different types of errors; the corresponding elimination strategies include: for geometric errors, using interpolation, smoothing, or resampling for correction; for texture errors, solving through texture repair, replacement, or remapping; for semantic errors, adjusting in combination with context information and prior knowledge.

[0107] S33, dynamically adjust the sampling density according to different regions and features of the model, introduce external auxiliary data (such as ground control points, high-precision maps, etc.), and fuse with existing data to further improve the accuracy and integrity of the model;

[0108] S34, identify and process repeated structures in the three-dimensional model, such as multiple scanning results of building outer walls, and reduce redundant information through algorithm optimization;

[0109] S35, based on physical principles and scene characteristics, construct a realistic lighting model to simulate lighting effects under different time and weather conditions;

[0110] S36, obtain texture materials through a texture material library, and accurately map the texture materials to the model surface based on texture mapping technology (such as UV unfolding, normal mapping, etc.).

[0111] The working principle of the above technical solution is: detailed classification of errors in the three-dimensional model, such as geometric errors (including size deviation, shape distortion, etc.), texture errors (texture blur, misplacement, etc.), semantic errors (object recognition error, inaccurate attribute labeling, etc.); using advanced image processing and machine learning algorithms, non-invasive identification of three-dimensional models, that is, automatically identifying and marking various errors without damaging the original model structure; develop special elimination strategies for different types of errors. For example, for geometric errors, model correction algorithms or reference external data for calibration may be used; for texture errors, retexturing or optimizing texture mapping techniques may be needed; dynamically adjust the sampling density according to different areas and features of the model (such as detail richness, importance, etc.). Increase sampling points in key areas to improve the detail performance and accuracy of the model; introduce external auxiliary data (such as ground control points, high-precision maps, etc.) and fuse with existing three-dimensional model data. This process corrects and supplements the model through high-precision data sources, further improving the accuracy and integrity of the model; in three-dimensional models, there are often repeated structures (such as multiple scanning results of building exterior walls) due to multiple scans or improper data processing. Identify these repeated structures through algorithms and effectively process them; for identified repeated structures, reduce redundant information through algorithm optimization to avoid confusion and unnecessary computational burden in model display and application; based on physical principles and scene characteristics, construct a realistic lighting model. This model can simulate the lighting effects under different times (such as day and night changes), weather conditions (such as sunny, cloudy, rainy, etc.); use the lighting model to simulate the lighting effects of the three-dimensional model, making the model present a more realistic and lively visual effect under different lighting conditions; obtain rich texture materials from the texture material library, including texture pictures of different materials, colors, and textures; use advanced texture mapping techniques such as UV unwrapping and normal mapping to accurately map texture materials to the surface of the three-dimensional model. This process not only enhances the visual effect of the model, but also makes the model surface more delicate and realistic.

[0112] The technical scheme has the effects that: through detailed classification and automatic identification of errors in the three-dimensional model, the defects in the model can be accurately found out, providing accurate targets for subsequent correction; special elimination strategies are formulated for different types of errors to effectively reduce or eliminate errors, improving the accuracy and precision of the model; the sampling density is dynamically adjusted according to different regions and features of the model to ensure that key regions have higher detail performance, making the model more detailed and realistic; external auxiliary data is introduced and fused with existing data to further improve the accuracy and integrity of the model, especially for regions where original data is insufficient or difficult to obtain directly; repeated structures in the three-dimensional model are identified and processed to reduce redundant information through algorithm optimization, making the model structure more concise and efficient, while reducing the burden of storage and processing; the light model constructed based on physical principles and scene characteristics can simulate the lighting effect under different time and weather conditions, making the model present a real and lively visual effect in different environments; the rich texture materials are accurately mapped to the model surface using texture mapping technology, not only enhancing the visual effect of the model, but also making the model surface more delicate and realistic, improving the overall realism; the non-invasive identification algorithm automatically identifies errors in the three-dimensional model, reducing the workload of manual inspection and improving work efficiency; the technical scheme of the entire S3 stage contains a series of automatic processing processes such as error classification, elimination, sampling density adjustment, and repeated structure processing, reducing manual intervention and improving the automation level; the optimized and enhanced three-dimensional model can be applied to more fields such as urban planning, architectural design, virtual reality, game development, etc., providing high-quality three-dimensional data support for different industries; in the fields of virtual reality, games, etc., the optimized three-dimensional model can provide a more realistic and immersive user experience, enhancing user engagement and satisfaction.

[0113] In an embodiment of the present application, the S33 comprises:

[0114] Through image processing and machine learning algorithms, key feature regions in the three-dimensional model are automatically identified, such as edges, corner points, and texture-rich areas; the sampling density of each region is dynamically planned according to the importance and complexity of the feature regions; for key feature regions, the sampling points are increased to improve the accuracy; for smooth regions, the sampling points are appropriately reduced to reduce data redundancy.

[0115] Based on the planning results, an adaptive sampling algorithm is used to dynamically adjust the sampling density during model construction or optimization;

[0116] External auxiliary data (ground control points, high-precision maps) is obtained and preprocessed, including coordinate conversion, denoising, accuracy evaluation, etc., and a data fusion operation is performed to fuse the external auxiliary data with the existing three-dimensional model data; after the fusion is completed, the accuracy of the fusion results is evaluated;

[0117] Utilize multi-source data (such as data collected by different sensors, data at different time points, etc.) for mutual verification, discover and correct potential errors in the model, and use surface reconstruction techniques (such as point cloud-based surface reconstruction, mesh optimization, etc.) to refine the surface of the model;

[0118] Establish a real-time feedback mechanism to monitor and evaluate each link in the model construction and optimization process, and if problems or deficiencies are found, feedback and adjustments are made;

[0119] According to the real-time feedback results, develop an iterative optimization strategy to improve the accuracy and detail performance of the model through multiple iterations.

[0120] The working principle of the above technical solution is: using image processing and machine learning algorithms to automatically identify key feature areas in the three-dimensional model, such as edges, corners, and texture-rich areas. These areas usually have an important impact on the accuracy and visual effect of the model; according to the importance and complexity of the feature areas, dynamically plan the sampling density of each area. For key feature areas, increase the sampling points to improve the accuracy; for smooth areas, appropriately reduce the sampling points to reduce data redundancy; during the model construction or optimization process, use an adaptive sampling algorithm to dynamically adjust the sampling density according to the planning results. This can ensure the fineness of the model and improve the processing efficiency; obtain external auxiliary data (such as ground control points, high-precision maps) and preprocess them, including coordinate conversion, denoising, accuracy evaluation, etc., to ensure the accuracy and usability of the data; fuse the preprocessed external auxiliary data with the existing three-dimensional model data. During the fusion process, the compatibility, consistency, and accuracy requirements of the data need to be considered; evaluate the accuracy of the fused model to ensure that the fusion operation achieves the expected results in terms of improving the accuracy and completeness of the model; use multi-source data (such as data collected by different sensors, data at different time points, etc.) for mutual verification to discover and correct potential errors in the model. This helps to improve the accuracy and reliability of the model; use point cloud-based surface reconstruction, mesh optimization, and other surface reconstruction techniques to refine the surface of the model. These techniques can improve the smoothness and realism of the model surface, making it more consistent with the actual scene; establish a real-time feedback mechanism to monitor and evaluate each link in the model construction and optimization process. Once problems or deficiencies are found, feedback and adjustments are made immediately; according to the real-time feedback results, develop an iterative optimization strategy. Through multiple iterations, continuously improve the accuracy and detail performance of the model until the desired goal is achieved. This iterative optimization approach helps to gradually approach the optimal solution and improve the overall quality of the model.

[0121] The effects of the above technical solutions are: automatically identifying key feature regions through image processing and machine learning algorithms, and dynamically planning sampling density according to their importance and complexity. This strategy ensures that key feature regions have enough sampling points to improve accuracy, while smooth regions reduce sampling points to reduce data redundancy. This ensures both the accuracy and efficiency of the model; mutual verification of multi-source data can discover and correct potential errors in the model. At the same time, through surface reconstruction techniques such as point cloud-based surface reconstruction and mesh optimization, the surface of the model is refined to improve the smoothness and realism of the surface. These measures collectively improve the accuracy and detail performance of the model; during model construction or optimization, an adaptive sampling algorithm is used to dynamically adjust the sampling density. This algorithm can automatically adjust the sampling strategy according to the actual situation of the model, avoiding unnecessary calculation waste and improving processing efficiency; a real-time feedback mechanism is established to monitor and evaluate each link in the model construction and optimization process. Once problems or deficiencies are found, feedback and adjustments are made immediately. At the same time, based on the real-time feedback results, an iterative optimization strategy is developed to continuously improve the accuracy and detail performance of the model through multiple iterations. This iterative optimization approach can quickly approach the optimal solution, improving the efficiency of model construction and optimization; through surface reconstruction techniques such as point cloud-based surface reconstruction and mesh optimization, the surface of the model is refined. These techniques can significantly improve the smoothness and realism of the model surface, making it more consistent with the actual scene; external auxiliary data (such as ground control points and high-precision maps) are fused with existing three-dimensional model data. These external data usually have higher accuracy and completeness, and through fusion, the accuracy and completeness of the model can be further improved. At the same time, the fused model is also more realistic and rich in visual effects; mutual verification of multi-source data can discover and correct potential errors in the model. This verification mechanism improves the reliability and stability of the model, reducing model problems caused by data errors or inconsistencies; the real-time feedback mechanism can quickly identify problems or deficiencies in the model construction and optimization process and provide feedback and adjustments. This mechanism ensures the stability and controllability of the model during construction and optimization.

[0122] In one embodiment of the present application, the S4 comprises:

[0123] S41, through the real-time monitoring system, the data of each link of the data acquisition system, the processing system, the storage system, etc. is comprehensively monitored, and is gathered and integrated;

[0124] S42, through the monitoring system, real-time feedback data is collected, including sensor status, data processing efficiency, model quality evaluation results, etc. The collected feedback data is analyzed and evaluated in depth to identify potential problems and bottlenecks;

[0125] S43, present the analysis results to relevant personnel (project managers or technical personnel) in a visualized manner, and develop dynamic adjustment strategies based on real-time feedback data and changes in project requirements;

[0126] S44, issue the developed strategies to various execution units (such as sensors, processing nodes, etc.) through the monitoring system, and automatically execute the strategies;

[0127] S45, evaluate and verify the execution effect of the strategies based on the execution results, and adjust and optimize the strategies according to the evaluation results.

[0128] The working principle of the above technical solution is as follows: through real-time monitoring systems, the data of each link of the data acquisition system, the processing system, the storage system, etc. is comprehensively monitored. These monitoring systems can capture the running state and performance indicators of each link in real time, such as the working state of the sensor, the speed and efficiency of data processing, the capacity and stability of data storage, etc. The collected data is aggregated and integrated into a unified data platform, providing a basis for subsequent data analysis and evaluation; the monitoring system not only collects real-time running data, but also collects real-time feedback data from each link, including sensor status, data processing efficiency, model quality evaluation results, etc. These feedback data reflect the actual running situation and performance of the system. Then, the collected feedback data is analyzed and evaluated in depth, and potential problems and bottlenecks are identified using data mining, machine learning and other technical means. These analysis results provide an important basis for subsequent strategy development; based on real-time feedback data and changes in project requirements, dynamic adjustment strategies are developed. These strategies aim to solve current problems, optimize system performance, and improve data quality and processing efficiency. In order to more intuitively display the analysis results and strategy scheme, the analysis results are presented to relevant personnel (such as project managers or technical personnel) in a visualized manner. Visual presentation helps relevant personnel quickly understand the problem and accurately grasp the strategy direction and focus; the developed strategies are issued to various execution units (such as sensors, processing nodes, etc.) through the monitoring system. These execution units will automatically adjust the working state and parameter settings according to the strategy requirements after receiving the strategy, thereby realizing the automatic execution of the strategy. This automatic execution mechanism improves the efficiency and accuracy of strategy implementation, reduces the possibility of human intervention and errors; the execution effect of the strategies is evaluated and verified based on the execution results. By comparing and analyzing the data changes and performance indicators before and after execution, it is evaluated whether the actual effect of the strategy meets the expected target. If the strategy effect is not ideal or there are problems, the strategy is adjusted and optimized according to the evaluation results. This cyclic iteration process helps to continuously optimize system performance, improve data quality and processing efficiency.

[0129] The effect of the above technical scheme is that: through the real-time monitoring system, the data of each link such as data acquisition, processing and storage can be obtained in real time, so that the system state can be grasped in time. At the same time, collecting real-time feedback data enables the project team to quickly respond to system changes, identify potential problems, and thus realize dynamic adjustment and optimization; based on real-time feedback data and project demand changes, a dynamic adjustment strategy is formulated. This flexibility ensures that the system can continuously adapt to changes in external environment and internal conditions, and maintain an efficient and stable running state; the data of each link are comprehensively monitored, aggregated and integrated to form a comprehensive data view. This provides rich data resources for the project team to support data-based decision-making process; the collected feedback data are deeply analyzed and evaluated to identify potential problems and bottlenecks. This data-driven method improves the accuracy and scientificity of decision-making, and reduces subjectivity and blindness; the analysis results are presented to relevant personnel in a visualized manner. This intuitive display method helps project managers and technical personnel quickly understand the system state and problem, improves communication efficiency and decision-making speed; through the visualized platform, team members of different roles can share information and opinions, promote cross-departmental cooperation and communication, and form a joint force to promote project progress; the formulated strategy is issued to each execution unit through the monitoring system to realize automatic execution of the strategy. This automatic mechanism reduces the possibility of manual intervention and errors, and improves the execution efficiency and accuracy; through real-time monitoring and data analysis, resource bottlenecks and optimization points can be found in time, so as to optimize resource allocation and improve resource utilization and overall efficiency; the execution effect of the strategy is evaluated and verified based on the execution result, and the strategy is adjusted and optimized according to the evaluation result. This continuous improvement mechanism helps continuously improve system performance and data quality, and ensures the smooth realization of project goals; through the close cooperation of real-time monitoring, data analysis, dynamic adjustment and continuous improvement, the S4 technical scheme provides strong support for the project team, and helps improve the project success rate and customer satisfaction.

[0130] In one embodiment of the present application, an electronic device includes a memory, a processor, and a computer program stored on the memory and executable on the memory, and the processor executes the program to implement the data fast acquisition method for real scene three-dimensional technology according to any one of the above.

[0131] In one embodiment of the present application, a non-transitory computer readable storage medium has a computer program stored thereon, and the program is executed by a processor to implement the data fast acquisition method for real scene three-dimensional technology according to any one of the above.

[0132] Obviously, many modifications and variations of the present application are possible in light of the above teachings. It is, therefore, to be understood that within the scope of the appended claims and their equivalents, the application can be practiced otherwise than as specifically described.

Claims

1. A method for rapid data acquisition in real-scene 3D technology, characterized in that, The method includes: S1. Collect raw data through a data acquisition system based on multi-source sensors, and plan and schedule the raw data acquisition task by using a cloud computing platform and combining it with GIS data. S2. During the data acquisition process, the raw data is preprocessed in real time through edge computing nodes, and the raw data from multiple sources is fused through a data fusion algorithm to generate a three-dimensional model. S3. Using artificial intelligence algorithms, the fused 3D model is automatically optimized and corrected; and combined with lighting simulation and texture mapping technology, the realism and visual effect of the model are enhanced. S4. Monitor the entire data acquisition and processing process through a real-time monitoring system; dynamically adjust data acquisition and processing strategies based on real-time feedback data; including: S41. Conduct comprehensive monitoring of data from all stages through a real-time monitoring system, and then aggregate and integrate the data. S42. Collect real-time feedback data through the monitoring system, conduct in-depth analysis and evaluation of the collected feedback data, and identify potential problems and bottlenecks; S43. Present the analysis results to relevant personnel in a visual manner, and formulate dynamic adjustment strategies based on real-time feedback data and changes in project requirements; S44. The established strategy is distributed to each execution unit through the monitoring system, and the strategy is executed automatically; S45. Evaluate and verify the effectiveness of the strategy based on the execution results, and adjust and optimize the strategy according to the evaluation results.

2. The method for rapid data acquisition for real-scene 3D technology according to claim 1, characterized in that, S1 includes: S11. Clarify the purpose and requirements of data collection, select data sources from multiple GIS data sources, and preprocess the selected GIS data; S12. Merge the preprocessed GIS data to form a unified spatial database; S13. Based on the requirements analysis results, list the relevant indicators of the required sensors, calibrate the selected sensors, and determine the sensor deployment plan. S14. Based on GIS data and sensor deployment scheme, plan the data acquisition route, and set the data acquisition time window based on multiple factors; and formulate a collaborative working strategy among multiple source sensors. S15. Assign the planned tasks to each sensor and set the task priority and execution order; establish a real-time monitoring mechanism to monitor the working status of the sensors in real time through a wireless communication network. S16. Based on real-time monitoring results, activate the emergency plan and handle any abnormal situations that occur.

3. The method for rapid data acquisition for real-scene 3D technology according to claim 2, characterized in that, S12 includes: Convert GIS data from different sources into a unified format; and enhance key features in the GIS data. Data fusion operations are performed based on a preset fusion scheme, and the pre-processed GIS data is fused using selected algorithms and tools. The quality of the fused data is assessed, and the fusion algorithm or parameters are iteratively optimized based on the assessment results. The merged GIS data is imported into a spatial database, indexed and managed for metadata, and the data is managed for security, with a data backup strategy developed.

4. The method for rapid data acquisition for real-scene 3D technology according to claim 1, characterized in that, The S2 includes: S21. Select edge computing node devices according to data processing requirements; deploy edge computing nodes at the data acquisition site and connect the edge computing nodes with sensors through the Internet of Things; S22. The edge computing node receives raw data from the sensor, verifies the data integrity and consistency, performs noise reduction on the raw data through a filtering algorithm, and compresses the denoised data. S23. Accurately match multi-source data through feature extraction and matching algorithms, and perform data fusion through data fusion strategies; evaluate the quality of the fused data. S24. Based on the fused data, the data is reconstructed using a 3D reconstruction algorithm; a preliminary 3D model framework is generated based on the reconstructed data, and the preliminary model is verified.

5. The method for rapid data acquisition for real-scene 3D technology according to claim 1, characterized in that, The S3 includes: S31. Classify and analyze the errors in the 3D model, and automatically identify the errors in the 3D model through a non-invasive recognition algorithm; S32. Develop corresponding elimination strategies for different types of errors; S33. Based on different regions and features of the model, dynamically adjust the sampling density, introduce external auxiliary data, and fuse it with existing data to further improve the accuracy and completeness of the model; S34. Identify and process repetitive structures in the 3D model, and reduce redundant information through algorithm optimization; S35. Based on physical principles and scene characteristics, construct a lighting model to simulate the lighting effects under different times and weather conditions; S36. Obtain texture materials from the texture material library, and accurately map the texture materials onto the model surface based on texture mapping technology.

6. The method for rapid data acquisition for real-scene 3D technology according to claim 5, characterized in that, S33 includes: By using image processing and machine learning algorithms, key feature regions in the 3D model are automatically identified, and the sampling density of each region is dynamically planned according to the importance and complexity of the feature regions. Based on the planning results, an adaptive sampling algorithm is adopted to dynamically adjust the sampling density during the model building or optimization process; External auxiliary data is acquired, preprocessed, and then a data fusion operation is performed to fuse the external auxiliary data with the existing 3D model data; after the fusion is completed, the accuracy of the fusion result is evaluated. By using multi-source data for cross-verification, potential errors in the model can be discovered and corrected. Surface reconstruction technology is used to refine the model surface. Establish a real-time feedback mechanism to monitor and evaluate each stage of the model building and optimization process. If problems or deficiencies are found, feedback and adjustments will be made. Based on real-time feedback, an iterative optimization strategy is developed, and the accuracy and detail representation of the model are improved through multiple iterations.

7. The method for rapid data acquisition for real-scene 3D technology according to claim 5, characterized in that, The corresponding elimination strategies include: for geometric errors, correction is performed using interpolation, smoothing, or resampling; for texture errors, resolution is achieved through texture repair, replacement, or remapping; and for semantic errors, adjustments are made by combining contextual information and prior knowledge.

8. An electronic device, characterized in that, The device includes a memory, a processor, and a computer program stored on and executable on the memory, wherein the processor executes the program to implement the rapid data acquisition method for real-scene 3D technology as described in any one of claims 1-7.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the rapid data acquisition method for real-scene 3D technology as described in any one of claims 1-7.

Images